Dialog-context dependent language modeling combining n-grams and stochastic context-free grammars

We present our research on dialog dependent language modeling. In accordance with a speech (or sentence) production model in a discourse we split language modeling into two components; namely, dialog dependent concept modeling and syntactic modeling. The concept model is conditioned on the last question prompted by the dialog system and it is structured using n-grams. The syntactic model, which consists of a collection of stochastic context-free grammars one for each concept, describes word sequences that may be used to express the concepts. The resulting LM is evaluated by rescoring N-best lists. We report significant perplexity improvement with moderate word error rate drop within the context of the CU Communicator System; a dialog system for making travel plans by accessing information about flights, hotels and car rentals.

[1]  Wayne Ward,et al.  Flexible use of semantic constraints in speech recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Jan Robin Rohlicek,et al.  Statistical language modeling combining N-gram and context-free grammars , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Wayne H. Ward,et al.  A language model combining trigrams and stochastic context-free grammars , 1998, ICSLP.

[4]  Paolo Baggia,et al.  Specialized language models using dialogue predictions , 1996, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Xuedong Huang,et al.  A unified context-free grammar and n-gram model for spoken language processing , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[6]  J. Baker.  Trainable grammars for speech recognition , 1979 .

[7]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Frank Wessel,et al.  Robust dialogue-state dependent language modeling using leaving-one-out , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[9]  Sheryl R. Young,et al.  The MINDS System: Using Context and Dialog to Enhance Speech Recognition , 1989, HLT.

[10]  Andreas Kellner,et al.  PADIS - An automatic telephone switchboard and directory information system , 1997, Speech Communication.

[11]  Hauke Schramm,et al.  The thoughtful elephant: strategies for spoken dialog systems , 2000, IEEE Trans. Speech Audio Process..

[12]  Wayne H. Ward,et al.  THE CU COMMUNICATOR SYSTEM 1 , 1999 .

[13]  Heinrich Niemann,et al.  Combining stochastic and linguistic language models for recognition of spontaneous speech , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.